Offline Changepoint Detection With Gaussian Processes

Janneke Verbeek, Tom Heskes, Yuliya Shapovalova
Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, PMLR 286:4329-4348, 2025.

Abstract

This work proposes Segmenting changepoint Gaussian process regression (SegCPGP), an offline changepoint detection method that integrates Gaussian process regression with the changepoint kernel, the likelihood ratio test and binary search. We use the spectral mixture kernel to detect various types of changes without prior knowledge of their type. SegCPGP outperforms state-of-the-art methods when detecting various change types in synthetic datasets; in real world changepoint detection datasets, it performs on par with its competitors. While its hypothesis test shows slight miscalibration, we find SegCPGP remains reasonably reliable.

Cite this Paper

BibTeX
@InProceedings{pmlr-v286-verbeek25a, title = {Offline Changepoint Detection With Gaussian Processes}, author = {Verbeek, Janneke and Heskes, Tom and Shapovalova, Yuliya}, booktitle = {Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence}, pages = {4329--4348}, year = {2025}, editor = {Chiappa, Silvia and Magliacane, Sara}, volume = {286}, series = {Proceedings of Machine Learning Research}, month = {21--25 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v286/main/assets/verbeek25a/verbeek25a.pdf}, url = {https://proceedings.mlr.press/v286/verbeek25a.html}, abstract = {This work proposes Segmenting changepoint Gaussian process regression (SegCPGP), an offline changepoint detection method that integrates Gaussian process regression with the changepoint kernel, the likelihood ratio test and binary search. We use the spectral mixture kernel to detect various types of changes without prior knowledge of their type. SegCPGP outperforms state-of-the-art methods when detecting various change types in synthetic datasets; in real world changepoint detection datasets, it performs on par with its competitors. While its hypothesis test shows slight miscalibration, we find SegCPGP remains reasonably reliable.} }
Endnote
%0 Conference Paper %T Offline Changepoint Detection With Gaussian Processes %A Janneke Verbeek %A Tom Heskes %A Yuliya Shapovalova %B Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2025 %E Silvia Chiappa %E Sara Magliacane %F pmlr-v286-verbeek25a %I PMLR %P 4329--4348 %U https://proceedings.mlr.press/v286/verbeek25a.html %V 286 %X This work proposes Segmenting changepoint Gaussian process regression (SegCPGP), an offline changepoint detection method that integrates Gaussian process regression with the changepoint kernel, the likelihood ratio test and binary search. We use the spectral mixture kernel to detect various types of changes without prior knowledge of their type. SegCPGP outperforms state-of-the-art methods when detecting various change types in synthetic datasets; in real world changepoint detection datasets, it performs on par with its competitors. While its hypothesis test shows slight miscalibration, we find SegCPGP remains reasonably reliable.
APA
Verbeek, J., Heskes, T. & Shapovalova, Y.. (2025). Offline Changepoint Detection With Gaussian Processes. Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 286:4329-4348 Available from https://proceedings.mlr.press/v286/verbeek25a.html.

Related Material